GPT-3 zero-shot models flag social norm violations across two large datasets

ArtificialOther · x · 2026-09-24

A Scientific Reports paper by Yair Neuman and Yochai Cohen presents a novel approach to identifying social norm violations using GPT-3, zero-shot classification, and automatic rule discovery to build simple predictive models grounded in psychological knowledge.

Original post →

More from Research

Research channel →